Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/prowler-cloud/prowler/prowler-commitnpx skills add prowler-cloud/prowler --skill prowler-commitgit clone --depth 1 https://github.com/prowler-cloud/prowlerWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00033 | $0.01063 |
| Opus 5 | $0.00016 | $0.00531 |
| Sonnet 5 | $0.00007 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
prowler-commit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critical Rules
- ALWAYS use conventional-commits format:
type(scope): description - ALWAYS keep the first line under 72 characters
- ALWAYS ask for user confirmation before committing
- NEVER be overly specific (avoid counts like "6 subsections", "3 files")
- NEVER include implementation details in the title
- NEVER use
-nflag unless user explicitly requests it - NEVER use
git push --forceorgit push -f(destructive, rewrites history) - NEVER proactively offer to commit - wait for user to explicitly request it
Commit Format
type(scope): concise description
- Key change 1
- Key change 2
- Key change 3
Types
| Type | Use When |
|---|---|
feat |
New feature or functionality |
fix |
Bug fix |
docs |
Documentation only |
chore |
Maintenance, dependencies, configs |
refactor |
Code change without feature/fix |
test |
Adding or updating tests |
perf |
Performance improvement |
style |
Formatting, no code change |
Scopes
| Scope | When |
|---|---|
api |
Changes in api/ |
ui |
Changes in ui/ |
sdk |
Changes in prowler/ |
mcp |
Changes in mcp_server/ |
skills |
Changes in skills/ |
ci |
Changes in .github/ |
docs |
Changes in docs/ |
| omit | Multiple scopes or root-level |
Good vs Bad Examples
Title Line
# GOOD - Concise and clear
feat(api): add provider connection retry logic
fix(ui): resolve dashboard loading state
chore(skills): add Celery documentation
docs: update installation guide
# BAD - Too specific or verbose
feat(api): add provider connection retry logic with exponential backoff and jitter (3 retries max)
chore(skills): add comprehensive Celery documentation covering 8 topics
fix(ui): fix the bug in dashboard component on line 45
Body (Bullet Points)
# GOOD - High-level changes
- Add retry mechanism for failed connections
- Document task composition patterns
- Expand configuration reference
# BAD - Too detailed
- Add retry with max_retries=3, backoff=True, jitter=True
- Add 6 subsections covering chain, group, chord
- Update lines 45-67 in dashboard.tsx
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 181 lines · 33 tokens per session scan A 59528bdd470c
prowler-commit is a skill published in the GitHub repository prowler-cloud/prowler (14,736 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 1,063 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ak-dev-code-quality
Code quality standards, formatting, commit conventions, and PR workflow for Agent Kernel development. Use this skill when making contributions, formatting code, writing commit messages, or preparing pull requests.
ponytail-sec-audit
Full project security audit. Scans the entire codebase across three passes: code that shouldn't exist, all dependencies assessed, all hardening findings. Produces a comprehensive numbered report with blast-radius narrative. Persists findings to .ponytail-sec/ for cross-scan tracking. For per-diff review use…
ponytail-sec
Security companion for active development. Scopes to the current diff or changed files. Three passes: YAGNI code review, new-dep assessment, and up to 3 material hardening findings. Lean by design — surfaces the one thing to fix before merging, not a backlog. Use ponytail-sec-audit for a full project scan.
git-workflow
Helps with git workflows including conventional commit messages, branching strategies, merge conflict resolution, and changelog generation. Triggers on: "git commit message", "branching strategy", "resolve conflict", "generate changelog".
conventional-commits
Write git commit messages that follow the Conventional Commits standard. Use when the user asks for a commit message, or gives a change summary or diff and wants it written up for git.
tunnel-manager-ssh-hardening
Harden and audit SSH access across a host fleet via the tunnel-manager MCP server — set up passwordless key auth, build a full-mesh trust, rotate SSH keys fleet-wide, distribute a shared ssh config, and run security / compliance / vulnerability audits against a host. Use when the agent must move a fleet off password…